Search Results - "Maziarz, Krzysztof"

PREFER: A New Predictive Modeling Framework for Molecular Discovery by Lanini, Jessica, Santarossa, Gianluca, Sirockin, Finton, Lewis, Richard, Fechner, Nikolas, Misztela, Hubert, Lewis, Sarah, Maziarz, Krzysztof, Stanley, Megan, Segler, Marwin, Stiefl, Nikolaus, Schneider, Nadine

“…Machine-learning and deep-learning models have been extensively used in cheminformatics to predict molecular properties, to reduce the need for direct…”
Get full text

Deep Learning for Rheumatoid Arthritis: Joint Detection and Damage Scoring in X-rays by Maziarz, Krzysztof, Krason, Anna, Wojna, Zbigniew

“…Recent advancements in computer vision promise to automate medical image analysis. Rheumatoid arthritis is an autoimmune disease that would profit from…”
Get full text

RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets by Gaiński, Piotr, Koziarski, Michał, Maziarz, Krzysztof, Segler, Marwin, Tabor, Jacek, Śmieja, Marek

“…Single-step retrosynthesis aims to predict a set of reactions that lead to the creation of a target molecule, which is a crucial task in molecular discovery…”
Get full text

Re-evaluating Retrosynthesis Algorithms with Syntheseus by Maziarz, Krzysztof, Tripp, Austin, Liu, Guoqing, Stanley, Megan, Xie, Shufang, Gaiński, Piotr, Seidl, Philipp, Segler, Marwin

“…Automated Synthesis Planning has recently re-emerged as a research area at the intersection of chemistry and machine learning. Despite the appearance of steady…”
Get full text

Retro-fallback: retrosynthetic planning in an uncertain world by Tripp, Austin, Maziarz, Krzysztof, Lewis, Sarah, Segler, Marwin, Hernández-Lobato, José Miguel

“…Retrosynthesis is the task of planning a series of chemical reactions to create a desired molecule from simpler, buyable molecules. While previous works have…”
Get full text

Are VAEs Bad at Reconstructing Molecular Graphs? by Muenkler, Hagen, Misztela, Hubert, Pikusa, Michal, Segler, Marwin, Schneider, Nadine, Maziarz, Krzysztof

“…Many contemporary generative models of molecules are variational auto-encoders of molecular graphs. One term in their training loss pertains to reconstructing…”
Get full text

Hashing Modulo Alpha-Equivalence by Maziarz, Krzysztof, Ellis, Tom, Lawrence, Alan, Fitzgibbon, Andrew, Jones, Simon Peyton

“…In many applications one wants to identify identical subtrees of a program syntax tree. This identification should ideally be robust to alpha-renaming of the…”
Get full text

Retrosynthetic Planning with Dual Value Networks by Liu, Guoqing, Xue, Di, Xie, Shufang, Xia, Yingce, Tripp, Austin, Maziarz, Krzysztof, Segler, Marwin, Qin, Tao, Zhang, Zongzhang, Liu, Tie-Yan

“…Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery…”
Get full text

Holistic Multi-View Building Analysis in the Wild with Projection Pooling by Wojna, Zbigniew, Maziarz, Krzysztof, Jocz, Łukasz, Pałuba, Robert, Kozikowski, Robert, Kokkinos, Iasonas

“…We address six different classification tasks related to fine-grained building attributes: construction type, number of floors, pitch and geometry of the roof,…”
Get full text

Evolutionary-Neural Hybrid Agents for Architecture Search by Maziarz, Krzysztof, Tan, Mingxing, Khorlin, Andrey, Georgiev, Marin, Gesmundo, Andrea

“…Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex…”
Get full text

Learning to Extend Molecular Scaffolds with Structural Motifs by Maziarz, Krzysztof, Jackson-Flux, Henry, Cameron, Pashmina, Sirockin, Finton, Schneider, Nadine, Stiefl, Nikolaus, Segler, Marwin, Brockschmidt, Marc

“…Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available,…”
Get full text

Flexible Multi-task Networks by Learning Parameter Allocation by Maziarz, Krzysztof, Kokiopoulou, Efi, Gesmundo, Andrea, Sbaiz, Luciano, Bartok, Gabor, Berent, Jesse

“…This paper proposes a novel learning method for multi-task applications. Multi-task neural networks can learn to transfer knowledge across different tasks by…”
Get full text

The Slow-coloring Game on Sparse Graphs: $k$-Degenerate, Planar, and Outerplanar by Gutowski, Grzegorz, Krawczyk, Tomasz, Maziarz, Krzysztof, West, Douglas B, Zając, Michał, Zhu, Xuding

“…The \emph{slow-coloring game} is played by Lister and Painter on a graph $G$. Initially, all vertices of $G$ are uncolored. In each round, Lister marks a…”
Get full text

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer by Shazeer, Noam, Mirhoseini, Azalia, Maziarz, Krzysztof, Davis, Andy, Le, Quoc, Hinton, Geoffrey, Dean, Jeff

“…The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active…”
Get full text